Scribd
Upload
67 views

Idea Regional Regression: Problems To Be Solved

The document discusses using regional regression to model relationships that vary spatially rather than assuming a single global relationship. It proposes discovering regions where the dependent and independent variables have a strong relationship and estimating separate regression functions for each region. Examples are given showing how relationships between variables can differ in different locations and why using human-defined boundaries like zip codes may not accurately capture the underlying spatial patterns in data.

Uploaded by

Bezan Melese
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
67 views

Idea Regional Regression: Problems To Be Solved

The document discusses using regional regression to model relationships that vary spatially rather than assuming a single global relationship. It proposes discovering regions where the dependent and independent variables have a strong relationship and estimating separate regression functions for each region. Examples are given showing how relationships between variables can differ in different locations and why using human-defined boundaries like zip codes may not accurately capture the underlying spatial patterns in data.

Uploaded by

Bezan Melese
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Idea Regional Regression

Our Approach: Use a separate regression function for different


regions.
Problem: Need to find regions with a strong relationship between
the dependent and independent variable.

Problems to be solved:
1. Discovering the Regions
2. Extracting Regional Regression
Functions
3. Develop a method to select which
regression function to use for a
new object to be predicted.

Source: http://www2.cs.uh.edu/~ceick/kdd/CE09.pdf
Motivation
Regional Knowledge & Coefficient Estimates
 In geo-referenced dataset, most relationships only exist at
regional level but not at the global level.

 1st law of geography: “Everything is related to everything else


but nearby things are more related than distant things” (Tobler)

 Coefficient estimates in geo-referenced datasets spatially


vary  we need regression methods to discover regional
coefficient estimates that captures underlying structure of
data.

 Using human-made boundaries (zip code etc.) is not good


idea since they do not reflect patterns in spatially variance.
Motivation
Geo-Regression Analysis Methods
 Regression Trees
 Data is split in a top-down approach using a greedy
algorithm; uses constants as regression functions
 Discovers only rectangular shapes
 Geographically Weighted Regression (GWR)
 an instance-based, local spatial statistical technique used
to analyze spatial non-stationarity.
 generates a separate regression for each possible query
point “online”determined using a grid or kernel
 a weight assigned to each observation that is based on its
distance to the query point.
Motivation
Example 1: Why We Need Regional Knowledge?

Arsenic

Fluoride

Regression Result: A positive linear regression line


(Arsenic increases with increasing Fluoride concentration)
Motivation
Example 1: Why We Need Regional Knowledge?
Location 1
Location 2
Arsenic

Fluoride

 A negative linear Regression line in both locations


(Arsenic decreases with increasing Fluoride concentration)
 A reflection of Simpson’s paradox[16].
Motivation

Example 2: Houston House Price Estimate

 Dependent variable: House_Price


 Independent variables: noOfRooms, squareFootage, yearBuilt,
havePool, attachedGarage, etc..
Motivation

Example 2: Houston House Price Estimate


 Global Regression (OLS) produces the coefficient
estimates, R2 value, and error etc.. a model
 This model assumes all areas have same coefficients
 E.g. attribute havePool has a coefficient of +9,000
(~having a pool adds $9,000 to a house price)
 In reality this changes. A house of $100K and a house of
$500K or different zip codes or locations.
 Having a pool in a house in luxury areas is very different
(~$40K) than having a pool in a house in Suburbs(~$5K).
Motivation

Example 2: Houston House Price Estimate


Solution: To apply local regression to each zip code
 produces 50+ sets of parameter estimates
 it captures spatial variations in the relationship better than
global model
 But it is very naïve and has problems
 there is spatial variation within zip codes
 assumes discontinuity but most spatial patterns are
continuous and they do not stop & start at the border.
Motivation

Example 2: Houston House Price Estimate

$350,000

$180,000

 Houses A, B have very similar characteristics


 OLS produces single parameter estimates for predictor variables
like noOfRooms, squareFootage, yearBuilt, etc
Motivation

Example 2: Houston House Price Estimate


 If we use zip code as regions, they are in same region
 If we use a grid structure
 They are in different regions but
some houses similar to B (lake
view) are in same region with A and
this will effect coefficient estimate
 More importantly, the house around
U-shape lake show similar pattern
and should be in the same region,
we miss important information.

You might also like